Find a story

Search Spins

Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.

3 results for “adversarial attack”

SPIN Processed News Frame: The Hype

Beyond Decision Boundaries: Relational Geometry Attacks on Contrastive Embedding Manifolds

Researchers introduced a new adversarial attack framework that corrupts the relational geometry of contrastive embedding manifolds—targeting similarity structure rather than classification decisions—and demonstrated severe performance degradation on verification systems like Markmatch.

Spin 65% Claim Present in Source AI Risk Moderate
arXiv Artificial Intelligence

Aug 12, 2026

SPIN Processed News Frame: The Hype

Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation

Researchers introduced an automated, multi-agent red-teaming system that synthesizes adversarial multimodal examples to improve MLLM content safety robustness, reducing false negatives by 16.7 percentage points on a public benchmark without human labeling.

Spin 75% Claim Present in Source AI Risk High
arXiv Artificial Intelligence

Jul 17, 2026

SPIN Processed News Frame: The Fog

Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications?

A new arXiv preprint identifies how adversarial data manipulations targeting electricity price forecasts can undermine industrial demand response profitability and decision integrity, revealing that attack impact depends critically on perturbation direction—not just magnitude.

Spin 25% Claim Present in Source AI Risk Moderate
arXiv Machine Learning

Jul 10, 2026